© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112006
    Prev
    Next
    INDEX
    Explanations

    action verb followed by object

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    if
    -1.51
    w
    -1.48
    balon
    -1.41
    wavering
    -1.40
    にも
    -1.40
    Ｐ
    -1.39
     costru
    -1.39
    barcelona
    -1.38
    relenting
    -1.38
     were
    -1.36
    POSITIVE LOGITS
    Ᏻ
    1.64
     parachoque
    1.59
    おわりに
    1.54
     malheure
    1.48
    蠃
    1.47
    </i>
    1.41
    眼下
    1.41
    だったり
    1.40
     اینکه
    1.39
     Arxivat
    1.39
    Activations Density 0.052%

    No Known Activations